Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d46ada151dcb45e5178226ddfcf60e400ea665b21ed62f2e6dc83164dad0ed0b
+oid sha256:d14cb15f544457a22c81518309ace1eb3136c69f7df58a18cc6279bab0226a12
 size 1421491284

run-3/checkpoint-6000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e49e5a76adc327e0bc247e2b6b1b3736b98416ff84867ab8b336e3df92315d5
+size 1421491284

run-3/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eac4a6acef9597059671d6bf747c527f1e4306fe29faf478e7d4725601574be
+size 2843215085

run-3/checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cd2a853c4125ae0f68f1a567db5c02fa512db0c699a79825c2bcf3ad6c2289
+size 14244

run-3/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0042df5bd93cd08bee7bdbd520829c1345988d0fa481a5605a1fe7fcd33edd
+size 1064

run-3/checkpoint-6000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-6000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-3/checkpoint-6000/trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.04289544235925,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 21.11298370361328,
+      "learning_rate": 7.3094294083621386e-06,
+      "loss": 0.5946,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7713711261749268,
+      "eval_loss": 0.4571286737918854,
+      "eval_runtime": 8.9295,
+      "eval_samples_per_second": 334.061,
+      "eval_steps_per_second": 20.942,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 29.37565803527832,
+      "learning_rate": 6.784326720979801e-06,
+      "loss": 0.4626,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7948374152183533,
+      "eval_loss": 0.42729610204696655,
+      "eval_runtime": 8.9768,
+      "eval_samples_per_second": 332.301,
+      "eval_steps_per_second": 20.831,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 14.413555145263672,
+      "learning_rate": 6.2592240335974636e-06,
+      "loss": 0.4072,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 29.383678436279297,
+      "learning_rate": 5.734121346215126e-06,
+      "loss": 0.271,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8012068271636963,
+      "eval_loss": 0.5310697555541992,
+      "eval_runtime": 8.9237,
+      "eval_samples_per_second": 334.277,
+      "eval_steps_per_second": 20.955,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 63.45195007324219,
+      "learning_rate": 5.2090186588327885e-06,
+      "loss": 0.218,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 0.6844168305397034,
+      "eval_runtime": 8.9499,
+      "eval_samples_per_second": 333.298,
+      "eval_steps_per_second": 20.894,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 2.47409725189209,
+      "learning_rate": 4.68391597145045e-06,
+      "loss": 0.1755,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 91.6016616821289,
+      "learning_rate": 4.1588132840681135e-06,
+      "loss": 0.1087,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8112637996673584,
+      "eval_loss": 0.9277348518371582,
+      "eval_runtime": 8.9394,
+      "eval_samples_per_second": 333.691,
+      "eval_steps_per_second": 20.919,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 2.8172037601470947,
+      "learning_rate": 3.6337105966857756e-06,
+      "loss": 0.0945,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8126047849655151,
+      "eval_loss": 0.8183598518371582,
+      "eval_runtime": 8.9732,
+      "eval_samples_per_second": 332.435,
+      "eval_steps_per_second": 20.84,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 13.743531227111816,
+      "learning_rate": 3.108607909303438e-06,
+      "loss": 0.0798,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 14.02478313446045,
+      "learning_rate": 2.5835052219211006e-06,
+      "loss": 0.0476,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 1.0811419486999512,
+      "eval_runtime": 8.9338,
+      "eval_samples_per_second": 333.9,
+      "eval_steps_per_second": 20.932,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 24.512935638427734,
+      "learning_rate": 2.058402534538763e-06,
+      "loss": 0.0503,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8149514198303223,
+      "eval_loss": 1.084620714187622,
+      "eval_runtime": 8.955,
+      "eval_samples_per_second": 333.11,
+      "eval_steps_per_second": 20.882,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 0.23952540755271912,
+      "learning_rate": 1.5332998471564256e-06,
+      "loss": 0.0356,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.4451727532664852e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.834532095744476e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2f9f37c7726a45700c6b9fea6814a536354b2056a30500c9b5dc834f2644fb
+size 5048

run-3/checkpoint-6500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-6500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce7d777570e4c718b466948ab4d68f8e9234dddbd48ff7336eb2c195f3e739f
+size 1421491284

run-3/checkpoint-6500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53aa92bffb882f046c31daee91d5cea70afc0727535b966e8e27ca8ef3acb3f8
+size 2843215085

run-3/checkpoint-6500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b28cbaa9c68efbca58f43b86c6ad1755913c10141a95f4a2b975006f0a22c6
+size 14244

run-3/checkpoint-6500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b480f66cb7931d977308ba2dd1cb500bd78b0ed2e464b8dcc1945a8d04c299
+size 1064

run-3/checkpoint-6500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-6500/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-3/checkpoint-6500/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.71313672922252,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 21.11298370361328,
+      "learning_rate": 7.3094294083621386e-06,
+      "loss": 0.5946,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7713711261749268,
+      "eval_loss": 0.4571286737918854,
+      "eval_runtime": 8.9295,
+      "eval_samples_per_second": 334.061,
+      "eval_steps_per_second": 20.942,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 29.37565803527832,
+      "learning_rate": 6.784326720979801e-06,
+      "loss": 0.4626,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7948374152183533,
+      "eval_loss": 0.42729610204696655,
+      "eval_runtime": 8.9768,
+      "eval_samples_per_second": 332.301,
+      "eval_steps_per_second": 20.831,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 14.413555145263672,
+      "learning_rate": 6.2592240335974636e-06,
+      "loss": 0.4072,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 29.383678436279297,
+      "learning_rate": 5.734121346215126e-06,
+      "loss": 0.271,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8012068271636963,
+      "eval_loss": 0.5310697555541992,
+      "eval_runtime": 8.9237,
+      "eval_samples_per_second": 334.277,
+      "eval_steps_per_second": 20.955,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 63.45195007324219,
+      "learning_rate": 5.2090186588327885e-06,
+      "loss": 0.218,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 0.6844168305397034,
+      "eval_runtime": 8.9499,
+      "eval_samples_per_second": 333.298,
+      "eval_steps_per_second": 20.894,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 2.47409725189209,
+      "learning_rate": 4.68391597145045e-06,
+      "loss": 0.1755,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 91.6016616821289,
+      "learning_rate": 4.1588132840681135e-06,
+      "loss": 0.1087,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8112637996673584,
+      "eval_loss": 0.9277348518371582,
+      "eval_runtime": 8.9394,
+      "eval_samples_per_second": 333.691,
+      "eval_steps_per_second": 20.919,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 2.8172037601470947,
+      "learning_rate": 3.6337105966857756e-06,
+      "loss": 0.0945,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8126047849655151,
+      "eval_loss": 0.8183598518371582,
+      "eval_runtime": 8.9732,
+      "eval_samples_per_second": 332.435,
+      "eval_steps_per_second": 20.84,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 13.743531227111816,
+      "learning_rate": 3.108607909303438e-06,
+      "loss": 0.0798,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 14.02478313446045,
+      "learning_rate": 2.5835052219211006e-06,
+      "loss": 0.0476,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 1.0811419486999512,
+      "eval_runtime": 8.9338,
+      "eval_samples_per_second": 333.9,
+      "eval_steps_per_second": 20.932,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 24.512935638427734,
+      "learning_rate": 2.058402534538763e-06,
+      "loss": 0.0503,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8149514198303223,
+      "eval_loss": 1.084620714187622,
+      "eval_runtime": 8.955,
+      "eval_samples_per_second": 333.11,
+      "eval_steps_per_second": 20.882,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 0.23952540755271912,
+      "learning_rate": 1.5332998471564256e-06,
+      "loss": 0.0356,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 91.77034759521484,
+      "learning_rate": 1.008197159774088e-06,
+      "loss": 0.0281,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.5654147911459604e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.834532095744476e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-6500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2f9f37c7726a45700c6b9fea6814a536354b2056a30500c9b5dc834f2644fb
+size 5048

run-3/checkpoint-7000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-3/checkpoint-7000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b53c4dd20f2faf80ee43c68ec656459e408c5431f825da09961486c83fb3ed9
+size 1421491284

run-3/checkpoint-7000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5b8c57f85fce261ab50fc8ff4c532052623349aadecea9330a729594089d74
+size 2843215085

run-3/checkpoint-7000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d53b70600e37eb5219d066d83aeabdfb68e2384a631a75a67cc1ad2f1dcd3bd
+size 14244

run-3/checkpoint-7000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf45c934eefb922608c18078dc1b08cfc743a972c0779dadced5f7d931242ad5
+size 1064

run-3/checkpoint-7000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-3/checkpoint-7000/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-3/checkpoint-7000/trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.383378016085791,
+  "eval_steps": 500,
+  "global_step": 7000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6702412868632708,
+      "grad_norm": 21.11298370361328,
+      "learning_rate": 7.3094294083621386e-06,
+      "loss": 0.5946,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7713711261749268,
+      "eval_loss": 0.4571286737918854,
+      "eval_runtime": 8.9295,
+      "eval_samples_per_second": 334.061,
+      "eval_steps_per_second": 20.942,
+      "step": 746
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 29.37565803527832,
+      "learning_rate": 6.784326720979801e-06,
+      "loss": 0.4626,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7948374152183533,
+      "eval_loss": 0.42729610204696655,
+      "eval_runtime": 8.9768,
+      "eval_samples_per_second": 332.301,
+      "eval_steps_per_second": 20.831,
+      "step": 1492
+    },
+    {
+      "epoch": 2.0107238605898123,
+      "grad_norm": 14.413555145263672,
+      "learning_rate": 6.2592240335974636e-06,
+      "loss": 0.4072,
+      "step": 1500
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 29.383678436279297,
+      "learning_rate": 5.734121346215126e-06,
+      "loss": 0.271,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8012068271636963,
+      "eval_loss": 0.5310697555541992,
+      "eval_runtime": 8.9237,
+      "eval_samples_per_second": 334.277,
+      "eval_steps_per_second": 20.955,
+      "step": 2238
+    },
+    {
+      "epoch": 3.351206434316354,
+      "grad_norm": 63.45195007324219,
+      "learning_rate": 5.2090186588327885e-06,
+      "loss": 0.218,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 0.6844168305397034,
+      "eval_runtime": 8.9499,
+      "eval_samples_per_second": 333.298,
+      "eval_steps_per_second": 20.894,
+      "step": 2984
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 2.47409725189209,
+      "learning_rate": 4.68391597145045e-06,
+      "loss": 0.1755,
+      "step": 3000
+    },
+    {
+      "epoch": 4.6916890080428955,
+      "grad_norm": 91.6016616821289,
+      "learning_rate": 4.1588132840681135e-06,
+      "loss": 0.1087,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8112637996673584,
+      "eval_loss": 0.9277348518371582,
+      "eval_runtime": 8.9394,
+      "eval_samples_per_second": 333.691,
+      "eval_steps_per_second": 20.919,
+      "step": 3730
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 2.8172037601470947,
+      "learning_rate": 3.6337105966857756e-06,
+      "loss": 0.0945,
+      "step": 4000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8126047849655151,
+      "eval_loss": 0.8183598518371582,
+      "eval_runtime": 8.9732,
+      "eval_samples_per_second": 332.435,
+      "eval_steps_per_second": 20.84,
+      "step": 4476
+    },
+    {
+      "epoch": 6.032171581769437,
+      "grad_norm": 13.743531227111816,
+      "learning_rate": 3.108607909303438e-06,
+      "loss": 0.0798,
+      "step": 4500
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 14.02478313446045,
+      "learning_rate": 2.5835052219211006e-06,
+      "loss": 0.0476,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 1.0811419486999512,
+      "eval_runtime": 8.9338,
+      "eval_samples_per_second": 333.9,
+      "eval_steps_per_second": 20.932,
+      "step": 5222
+    },
+    {
+      "epoch": 7.372654155495979,
+      "grad_norm": 24.512935638427734,
+      "learning_rate": 2.058402534538763e-06,
+      "loss": 0.0503,
+      "step": 5500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8149514198303223,
+      "eval_loss": 1.084620714187622,
+      "eval_runtime": 8.955,
+      "eval_samples_per_second": 333.11,
+      "eval_steps_per_second": 20.882,
+      "step": 5968
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 0.23952540755271912,
+      "learning_rate": 1.5332998471564256e-06,
+      "loss": 0.0356,
+      "step": 6000
+    },
+    {
+      "epoch": 8.71313672922252,
+      "grad_norm": 91.77034759521484,
+      "learning_rate": 1.008197159774088e-06,
+      "loss": 0.0281,
+      "step": 6500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8119342923164368,
+      "eval_loss": 1.1618958711624146,
+      "eval_runtime": 8.9459,
+      "eval_samples_per_second": 333.45,
+      "eval_steps_per_second": 20.903,
+      "step": 6714
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 1.1024620532989502,
+      "learning_rate": 4.830944723917506e-07,
+      "loss": 0.0243,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.6858355699447064e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.834532095744476e-06,
+    "per_device_train_batch_size": 16
+  }
+}

run-3/checkpoint-7000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2f9f37c7726a45700c6b9fea6814a536354b2056a30500c9b5dc834f2644fb
+size 5048

run-4/checkpoint-500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-4/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14cb15f544457a22c81518309ace1eb3136c69f7df58a18cc6279bab0226a12
+size 1421491284

run-4/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79776acb5bd33b62286f1476d5c1fc552b0be29205e363fd412da5be2a15449b
+size 2843215085

run-4/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e800d34865c69a00523e13179b1522643e92893a41c2f88770f3a867354a978
+size 14244

run-4/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7672c756766ae41681d0b7d09ff2893fa2d4d66166101397e256a62c802c19
+size 1064

run-4/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-4/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-4/checkpoint-500/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.6737967914438503,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7254441976547241,
+      "eval_loss": 0.515117347240448,
+      "eval_runtime": 9.0075,
+      "eval_samples_per_second": 331.167,
+      "eval_steps_per_second": 20.76,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7492457032203674,
+      "eval_loss": 0.4793011546134949,
+      "eval_runtime": 9.1228,
+      "eval_samples_per_second": 326.983,
+      "eval_steps_per_second": 20.498,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 12.898003578186035,
+      "learning_rate": 2.66142701656233e-06,
+      "loss": 0.5477,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5510487892159476.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.6327507452347134e-06,
+    "per_device_train_batch_size": 64
+  }
+}

run-4/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f13ce7f3e21ba47d51870a7b8fdab14095997596acbf90c0c730c82502c290
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2f9f37c7726a45700c6b9fea6814a536354b2056a30500c9b5dc834f2644fb
+oid sha256:b3f13ce7f3e21ba47d51870a7b8fdab14095997596acbf90c0c730c82502c290
 size 5048